{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/approaches-toward-physical-and-general-video","title":"Approaches Toward Physical and General Video Anomaly Detection","arxiv_id":"2112.07661","date":"2021-12-14","proceeding":null,"authors":["Laura Kart","Niv Cohen"],"abstract":"In recent years, many works have addressed the problem of finding never-seen-before anomalies in videos. Yet, most work has been focused on detecting anomalous frames in surveillance videos taken from security cameras. Meanwhile, the task of anomaly detection (AD) in videos exhibiting anomalous mechanical behavior, has been mostly overlooked. Anomaly detection in such videos is both of academic and practical interest, as they may enable automatic detection of malfunctions in many manufacturing, maintenance, and real-life settings. To assess the potential of the different approaches to detect such anomalies, we evaluate two simple baseline approaches: (i) Temporal-pooled image AD techniques. (ii) Density estimation of videos represented with features pretrained for video-classification. Development of such methods calls for new benchmarks to allow evaluation of different possible approaches. We introduce the Physical Anomalous Trajectory or Motion (PHANTOM) dataset, which contains six different video classes. Each class consists of normal and anomalous videos. The classes differ in the presented phenomena, the normal class variability, and the kind of anomalies in the videos. We also suggest an even harder benchmark where anomalous activities should be spotted on highly variable scenes.","url_abs":"https://arxiv.org/abs/2112.07661v1","url_pdf":"https://arxiv.org/pdf/2112.07661v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"approaches-toward-physical-and-general-video","repo_url":"https://github.com/laurarkart/Physical-Anomalous-Trajectory-or-Motion-PHANTOM-Dataset","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"anomaly-detection","task_name":"Anomaly Detection"},{"task_slug":"density-estimation","task_name":"Density Estimation"},{"task_slug":"general-action-video-anomaly-detection","task_name":"General Action Video Anomaly Detection"},{"task_slug":"physical-video-anomaly-detection","task_name":"Physical Video Anomaly Detection"},{"task_slug":"video-anomaly-detection","task_name":"Video Anomaly Detection"},{"task_slug":"video-classification","task_name":"Video Classification"}],"methods":[],"datasets_introduced":[{"slug":"phantom","name":"PHANTOM","full_name":"Physical Anomalous Trajectory or Motion (PHANTOM)"}],"methods_introduced":[],"results":[{"leaderboard":"/sota/general-action-video-anomaly-detection-on","task":"General Action Video Anomaly Detection","dataset":"Something-Something V2","model":"Pooled Image Level kNN","rank_in_archive_order":1,"of":3,"metrics":{"Architecture":"ViT","Avg. ROC-AUC":"0.58"},"uses_additional_data":true},{"leaderboard":"/sota/general-action-video-anomaly-detection-on","task":"General Action Video Anomaly Detection","dataset":"Something-Something V2","model":"Video Level features kNN","rank_in_archive_order":3,"of":3,"metrics":{"Architecture":"TimeSformer","Avg. ROC-AUC":"0.52"},"uses_additional_data":true},{"leaderboard":"/sota/physical-video-anomaly-detection-on-phantom","task":"Physical Video Anomaly Detection","dataset":"PHANTOM","model":"Pooled Image Level kNN","rank_in_archive_order":1,"of":3,"metrics":{"Architecture":"ViT","Avg. ROC-AUC":"0.78"},"uses_additional_data":true},{"leaderboard":"/sota/physical-video-anomaly-detection-on-phantom","task":"Physical Video Anomaly Detection","dataset":"PHANTOM","model":"Video Level features kNN","rank_in_archive_order":2,"of":3,"metrics":{"Architecture":"TimeSformer","Avg. ROC-AUC":"0.76"},"uses_additional_data":true}],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}